#vispec
Jialiang Kang, Han Shu, Wenshuo Li, Yingjie Zhai, Xinghao Chen: ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding https://arxiv.org/abs/2509.15235 https://arxiv.org/pdf/2509.15235 https://arxiv.org/html/2509.15235
September 22, 2025 at 6:30 AM
ViSpec adds vision‑aware speculative decoding to large VLMs, achieving a speedup beyond the prior 1.5× limit for real‑time multimodal AI. Read more: https://getnews.me/vispec-accelerates-vision-language-models-with-speculative-decoding/ #vispec #visionlanguage #speculativedecoding
September 23, 2025 at 12:35 PM
December's issue of @appliedspec.bsky.social is a special issue dedicated to #VISPEC2023, which took place June 14-16th in #Perugia, Italy. Check out the full issue here: https://buff.ly/4j5wKo6 #spectroscopy #conferences

For more information about VISPEC, click here: https://buff.ly/40oQzyz
January 6, 2025 at 11:32 AM
Jialiang Kang, Han Shu, Wenshuo Li, Yingjie Zhai, Xinghao Chen
ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding
https://arxiv.org/abs/2509.15235
September 22, 2025 at 9:26 AM